ABSTRACT
Minimal criterion co-evolution (MCC) is an evolutionary algorithm that uses a simple reproduction constraint between two interacting populations to drive an open-ended search process. While it has previously been applied to parameterise simple agents and environments, in this work we extend its use to the generation of art: synthesising both images and music. As a creative AI tool which does not require any data, the use of MCC emphasises the design of the creative medium.
Supplemental Material
Available for Download
Supplemental material.
- Margaret A Boden and Ernest A Edmonds. 2009. What is Generative Art? Digit. Creat. 20, 1--2 (2009), 21--46.Google ScholarCross Ref
- Sam Bond-Taylor, Adam Leach, Yang Long, and Chris G Willcocks. 2021. Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models. arXiv:2103.04922 (2021).Google Scholar
- Jonathan C Brant and Kenneth O Stanley. 2017. Minimal Criterion Coevolution: A New Approach to Open-ended Search. In GECCO.Google Scholar
- Jonathan C Brant and Kenneth O Stanley. 2020. Diversity Preservation in Minimal Criterion Coevolution Through Resource Limitation. In GECCO.Google Scholar
- Scott Draves and Erik Reckase. 2008. The Fractal Flame Algorithm. Technical Report. Spotworks.Google Scholar
- Yaroslav Ganin, Tejas Kulkarni, Igor Babuschkin, SM Ali Eslami, and Oriol Vinyals. 2018. Synthesizing Programs for Images Using Reinforced Adversarial Learning. In ICML.Google Scholar
- Leon A Gatys, Alexander S Ecker, and Matthias Bethge. 2016. Image Style Transfer Using Convolutional Neural Networks. In CVPR.Google Scholar
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In NeurIPS.Google Scholar
- Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-scale Update Rule Converge to a Local Nash Equilibrium. In NeurIPS.Google Scholar
- Kiyohito Iigaya, Sanghyun Yi, Iman A Wahle, Koranis Tanwisuth, and John P O'Doherty. 2021. Aesthetic Preference for Art Can Be Predicted From a Mixture of Low- and High-level Visual Features. Nat. Hum. Behav. 5, 6 (2021), 743--755.Google ScholarCross Ref
- Tero Karras, Samuli Laine, and Timo Aila. 2019. A Style-based Generator Architecture for Generative Adversarial Networks. In CVPR.Google Scholar
- Kevin Kilgour, Mauricio Zuluaga, Dominik Roblek, and Matthew Sharifi. 2018. Fréchet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms. arXiv:1812.08466 (2018).Google Scholar
- Joel Lehman and Kenneth O Stanley. 2008. Exploiting Open-endedness to Solve Problems Through the Search for Novelty. In ALIFE.Google Scholar
- Rosanne Liu, Joel Lehman, Piero Molino, Felipe Petroski Such, Eric Frank, Alex Sergeev, and Jason Yosinski. 2018. An Intriguing Failing of Convolutional Neural nNtworks and the CoordConv Solution. In NeurIPS.Google Scholar
- Claudio Mattiussi and Dario Floreano. 2003. Viability Evolution: Elimination and Extinction in Evolutionary Computation. Technical Report. Ecole Polytechnique Fédérale de Lausanne.Google Scholar
- Alexander Mordvintsev, Christopher Olah, and Mike Tyka. 2015. Inceptionism: Going Deeper into Neural Networks. https://research.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.htmlGoogle Scholar
- Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, et al. 2019. Pytorch: An Imperative Style, High-performance Deep Learning Library. In NeurIPS.Google Scholar
- Elena Popovici, Anthony Bucci, R Paul Wiegand, and Edwin D De Jong. 2012. Coevolutionary Principles. Springer, 987--1033.Google Scholar
- Justin K Pugh, Lisa B Soros, Paul A Szerlip, and Kenneth O Stanley. 2015. Confronting the Challenge of Quality Diversity. In GECCO.Google Scholar
- Alec Radford, Luke Metz, and Soumith Chintala. 2016. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. In ICLR.Google Scholar
- Juan J Romero and Penousal Machado. 2008. The Art of Artificial Evolution: A Handbook on Evolutionary Art and Music. Springer Science & Business Media.Google Scholar
- Jimmy Secretan, Nicholas Beato, David B D Ambrosio, Adelein Rodriguez, Adam Campbell, and Kenneth O Stanley. 2008. Picbreeder: Evolving Pictures Collaboratively Online. In SIGCHI.Google Scholar
- L Soros and Kenneth O Stanley. 2014. Identifying Necessary Conditions for Open-ended Evolution Through the Artificial Life World of Chromaria. In ALIFE.Google Scholar
- Kenneth O Stanley. 2007. Compositional Pattern Producing Networks: A Novel Abstraction of Development. Genet. Program. Evolvable Mach. 8, 2 (2007), 131--162.Google ScholarDigital Library
- Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. 2018. Deep Image Prior. In CVPR.Google Scholar
- Han Zhang, Ian Goodfellow, Dimitris Metaxas, and Augustus Odena. 2019. Self-attention Generative Adversarial Networks. In ICML.Google Scholar
Index Terms
- Minimal criterion artist collective
Recommendations
Minimal criterion coevolution: a new approach to open-ended search
GECCO '17: Proceedings of the Genetic and Evolutionary Computation ConferenceRecent studies have emphasized the merits of search processes that lack overarching objectives, instead promoting divergence by rewarding behavioral novelty. While this less objective search paradigm is more open-ended and divergent, it still differs ...
Open-ended evolution and open-endedness: Editorial introduction to the open-ended evolution i special issue
Nature's spectacular inventiveness, reflected in the enormous diversity of form and function displayed by the biosphere, is a feature of life that distinguishes living most strongly from nonliving. It is, therefore, not surprising that this aspect of ...
Open-endedness for the sake of open-endedness
Natural evolution keeps inventing new complex and intricate forms and behaviors. Digital evolution and genetic algorithms fail to create the same kind of complexity, not just because we still lack the computational resources to rival nature, but because ...
Comments